Postdoctoral Fellow - AI/ML Upstream Cell Culture Modeling & Process Development

Position Summary

The Upstream Process Development group within our BR&D organization is seeking a Postdoctoral Fellow to join a team of scientists and engineers focused on developing and optimizing mammalian cell culture processes for recombinant proteins and other modalities for early- and late-phase clinical trials.

This role will focus on developing and applying innovative mathematical and computational modeling approaches to characterize, understand, and predict the complex biological systems used in mammalian cell culture. The fellow will build mechanistic and data-driven models, including genome-scale and hybrid metabolic models, to predict cellular behavior, diagnose process bottlenecks, and rationally guide the design of feeding strategies and medium compositions. Where current development often relies on iterative empirical screening, this position aims to establish a model-guided approach that narrows the experimental search space before committing significant laboratory effort.

The fellow will also explore the use of these models within real-time monitoring and control frameworks, and will leverage machine learning to enable earlier, model-informed decisions such as clone selection based on predicted process performance. The work establishes a closed-loop cycle in which model predictions are validated experimentally and the resulting data continuously improves model accuracy. This position is well suited to a highly motivated scientist who wants to bridge computational modeling and hands-on bioprocess experimentation.

Responsibilities

• Develop and calibrate mechanistic and hybrid metabolic models of mammalian cell culture processes, integrating process data to predict cellular behavior and identify performance-limiting factors.
• Build computational pipelines that turn routine bioprocess data into model inputs and generate predicted metabolic flux distributions across the culture cycle.
• Apply machine learning and data-driven methods for performance prediction and to integrate model-derived features with experimental data.
• Use calibrated models to evaluate feeding strategies and medium compositions to enhance productivity.
• Design and execute cell culture experiments—from shake flask to bench-scale bioreactors—to generate datasets for model development, training, and validation.
• Collaborate with the Analytical team to develop multi-omics methods for metabolic model calibration.
• Integrate model-derived features into machine learning workflows to support earlier decisions, including predictive clone selection from earlier-stage process data.
• Investigate AI-assisted approaches to accelerate model building, validation, and reuse across projects, with human-in-the-loop decision support.
• Maintain rigorous documentation, communicate results through technical reports, presentations, and peer-reviewed publications, and collaborate across cross-functional teams.

Basic Requirements

• PhD in Chemical/Biochemical Engineering, Bioengineering, Systems Biology, Computational Biology, Metabolic Engineering, or a related field.
• Experience with constraint-based or genome-scale metabolic modeling.
• Hands-on experience designing and executing cell culture experiments with a working understanding of Batch, Fed-batch, and Intensified Processes.
• Qualified applicants must be authorized to work in the United States on a full-time basis. Lilly will not provide support for or sponsor work authorization or visas for this role, including but not limited to F-1 CPT, F-1 OPT, F-1 STEM OPT, J-1, H-1B, TN, O-1, E-3, H-1B1, or L-1.

Additional Preferences

• Strong foundation in mathematical modeling, reaction kinetics, and mammalian cell culture.
• Proficiency in Python, MATLAB, or similar scientific programming languages.
• Familiarity with process control concepts, including model predictive control or dynamic optimization.
• Understanding of mammalian (e.g., CHO) cell physiology and metabolism relevant to bioprocessing.
• Experience with analytical methods such as HPLC, UPLC, and mass spectrometry is a plus.
• Experience integrating omics data with mechanistic or hybrid models.
• Demonstrated expertise in machine learning and data-driven modeling is a plus.